From Forward Prediction Error and Backward Prediction Error to Orthogonal Data in Space (Lattice Predictor) and the Origin of a System to Pick up Another

Authors

  • Dr. Ziad Sobih

Keywords:

wiener theory, prediction, filters, stochastic gradient, learning and lattice filter

Abstract

In this paper, we will develop another class of linear filter which involve order update and time update. These filters have the important fact of order update. We will show a computationally efficient modular lattice-like architecture. This lead to a filter with computational complexity linear with the order which is the length. The design of order recursive adaptive filter can take two approaches. 1. Stochastic [16] gradient approach. This is Wiener theory. 2. Least squares approach. This is Kalman filter theory. The second approach is code demanding. We will start with the first approach.

How to Cite

Dr. Ziad Sobih. (2017). From Forward Prediction Error and Backward Prediction Error to Orthogonal Data in Space (Lattice Predictor) and the Origin of a System to Pick up Another. Global Journal of Computer Science and Technology, 17(G3), 1–10. Retrieved from https://computerresearch.org/index.php/computer/article/view/1632

From Forward Prediction Error and Backward Prediction Error to Orthogonal Data in Space (Lattice Predictor) and the Origin of a System to Pick up Another

Published

2017-10-15